Question on Code
zhenxing1992 opened this issue · 6 comments
thank you for your code , it's very helpful for me to study computer vision.
but it is shame that i can't run this code correctly,
i think it's maybe the matter of the edition of software
so, there is a issue i want to know that the edition of software, such us python, opencv,
what i used is python 2.7 pencv 3.2.0
thank you very much
what's the error you get? I used python 2.7 and opencv 3.2, right
When I run code 'python cifar.py --save logs/resnet_40_1_teacher --depth 40 --width 1', there is a error that from torchvision import cvtransforms, that means i can't import name cvtransforms.
Should I change the import part 'from torchvision import cvtransforms' to 'from torchvision import transforms as cvtransforms'?
@zhenxing1992 please follow the installation instructions in README, you need to install torchvision from my fork, it has cvtransforms.
thank you very much .
i will train again immediately.
I just merged #9, so that it works with vanilla pytorch and torchvision.
i made it , thank you very much.